mirrors/huggingface--peft
1
0
Fork 0
Code Issues Pull Requests Actions 2 Deployments Models Agent Notes Packages Projects Releases Wiki Activity

chore: import upstream snapshot with attribution
Build documentation / build (push) Failing after 0s
Details
Deploy "method_comparison" Gradio to Spaces / deploy (push) Has been cancelled
Details
Deploy "PEFT shop" Gradio app to Spaces / deploy (push) Has been cancelled
Details
tests on transformers main / tests (push) Has been cancelled
Details
tests / check_code_quality (push) Has been cancelled
Details
tests / tests (ubuntu-latest, 3.10) (push) Has been cancelled
Details
tests / tests (ubuntu-latest, 3.11) (push) Has been cancelled
Details
tests / tests (ubuntu-latest, 3.12) (push) Has been cancelled
Details
tests / tests (ubuntu-latest, 3.13) (push) Has been cancelled
Details
tests / tests (windows-latest, 3.10) (push) Has been cancelled
Details
tests / tests (windows-latest, 3.11) (push) Has been cancelled
Details
tests / tests (windows-latest, 3.12) (push) Has been cancelled
Details
tests / tests (windows-latest, 3.13) (push) Has been cancelled
Details
Secret Leaks / trufflehog (push) Has been cancelled
Details
CI security linting / zizmor latest via Cargo (push) Has been cancelled
Details

Browse Source
This commit is contained in:
wehub-resource-sync
2026-07-13 13:24:42 +08:00
commit caf324b09d
920 changed files with 335491 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
method_comparison/MetaMathQA/experiments/lora/llama-3.2-3B-rank10-target-mlp/adapter_config.json
+30
View File
@@ -0,0 +1,30 @@
{
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": null,
"bias": "none",
"corda_config": null,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": false,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 20,
"lora_bias": false,
"lora_dropout": 0.0,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"r": 10,
"rank_pattern": {},
"revision": null,
"target_modules": ["gate_proj", "up_proj", "down_proj"],
"task_type": "CAUSAL_LM",
"use_dora": false,
"use_rslora": false
}
method_comparison/MetaMathQA/experiments/lora/llama-3.2-3B-rank14-target-mlp-bdlora/adapter_config.json
+48
View File
@@ -0,0 +1,48 @@
{
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": null,
"bias": "none",
"corda_config": null,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": false,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 28,
"lora_bias": false,
"lora_dropout": 0.0,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"r": 14,
"rank_pattern": {},
"revision": null,
"target_modules": [
"gate_proj",
"up_proj",
"down_proj"
],
"task_type": "CAUSAL_LM",
"use_dora": false,
"use_rslora": false,
"use_bdlora": {
"target_modules_bd_a": [
"o_proj",
"down_proj"
],
"target_modules_bd_b": [
"q_proj",
"v_proj",
"k_proj",
"up_proj",
"gate_proj"
],
"nblocks": 2
}
}
method_comparison/MetaMathQA/experiments/lora/llama-3.2-3B-rank32-dora/adapter_config.json
+30
View File
@@ -0,0 +1,30 @@
{
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": null,
"bias": "none",
"corda_config": null,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": false,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 64,
"lora_bias": false,
"lora_dropout": 0.0,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"r": 32,
"rank_pattern": {},
"revision": null,
"target_modules": null,
"task_type": "CAUSAL_LM",
"use_dora": true,
"use_rslora": false
}
method_comparison/MetaMathQA/experiments/lora/llama-3.2-3B-rank32-lorafa/adapter_config.json
+30
View File
@@ -0,0 +1,30 @@
{
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": null,
"bias": "none",
"corda_config": null,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": false,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 64,
"lora_bias": false,
"lora_dropout": 0.0,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"r": 32,
"rank_pattern": {},
"revision": null,
"target_modules": null,
"task_type": "CAUSAL_LM",
"use_dora": false,
"use_rslora": false
}
method_comparison/MetaMathQA/experiments/lora/llama-3.2-3B-rank32-lorafa/training_params.json
+9
View File
@@ -0,0 +1,9 @@
{
"optimizer_type": "lora-fa",
"optimizer_kwargs": {
"r": 32,
"lora_alpha": 64,
"lr": 1e-4,
"weight_decay": 0.1
}
}
method_comparison/MetaMathQA/experiments/lora/llama-3.2-3B-rank32-mica/adapter_config.json
+30
View File
@@ -0,0 +1,30 @@
{
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": null,
"bias": "none",
"corda_config": null,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": false,
"init_lora_weights": "mica",
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 64,
"lora_bias": false,
"lora_dropout": 0.0,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"r": 32,
"rank_pattern": {},
"revision": null,
"target_modules": null,
"task_type": "CAUSAL_LM",
"use_dora": false,
"use_rslora": false
}
method_comparison/MetaMathQA/experiments/lora/llama-3.2-3B-rank32/adapter_config.json
+30
View File
@@ -0,0 +1,30 @@
{
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": null,
"bias": "none",
"corda_config": null,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": false,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 64,
"lora_bias": false,
"lora_dropout": 0.0,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"r": 32,
"rank_pattern": {},
"revision": null,
"target_modules": null,
"task_type": "CAUSAL_LM",
"use_dora": false,
"use_rslora": false
}
method_comparison/MetaMathQA/experiments/lora/llama-3.2-3B-rank64-rslora/adapter_config.json
+30
View File
@@ -0,0 +1,30 @@
{
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": null,
"bias": "none",
"corda_config": null,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": false,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 64,
"lora_bias": false,
"lora_dropout": 0.0,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"r": 64,
"rank_pattern": {},
"revision": null,
"target_modules": null,
"task_type": "CAUSAL_LM",
"use_dora": false,
"use_rslora": true
}
method_comparison/MetaMathQA/experiments/lora/llama-3.2-3B-rank64/adapter_config.json
+30
View File
@@ -0,0 +1,30 @@
{
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": null,
"bias": "none",
"corda_config": null,
"eva_config": null,
"exclude_modules": null,
"fan_in_fan_out": false,
"inference_mode": false,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 128,
"lora_bias": false,
"lora_dropout": 0.0,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"r": 64,
"rank_pattern": {},
"revision": null,
"target_modules": null,
"task_type": "CAUSAL_LM",
"use_dora": false,
"use_rslora": false
}